Training in progress, step 5800, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ac5f8e4c88e22045662bff62540fc3d959e16fa80465c20902b176dbe839e2d
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96b453b97915d7de132ef1e4141e1e13b35a825c783bcb2520882fbacf9fbb04
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01085b11d0c773a0b23923f1ee4859afa820f0d9e2f2f5d5ec65836c410edef0
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 44.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -10430,6 +10430,24 @@
|
|
| 10430 |
"mean_token_accuracy": 0.6601225137710571,
|
| 10431 |
"num_tokens": 21116083.0,
|
| 10432 |
"step": 5790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10433 |
}
|
| 10434 |
],
|
| 10435 |
"logging_steps": 5,
|
|
@@ -10449,7 +10467,7 @@
|
|
| 10449 |
"attributes": {}
|
| 10450 |
}
|
| 10451 |
},
|
| 10452 |
-
"total_flos": 1.
|
| 10453 |
"train_batch_size": 4,
|
| 10454 |
"trial_name": null,
|
| 10455 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10430 |
"mean_token_accuracy": 0.6601225137710571,
|
| 10431 |
"num_tokens": 21116083.0,
|
| 10432 |
"step": 5790
|
| 10433 |
+
},
|
| 10434 |
+
{
|
| 10435 |
+
"epoch": 44.57692307692308,
|
| 10436 |
+
"grad_norm": 0.0,
|
| 10437 |
+
"learning_rate": 2.103e-05,
|
| 10438 |
+
"loss": 1.7913,
|
| 10439 |
+
"mean_token_accuracy": 0.6423264652490616,
|
| 10440 |
+
"num_tokens": 21133615.0,
|
| 10441 |
+
"step": 5795
|
| 10442 |
+
},
|
| 10443 |
+
{
|
| 10444 |
+
"epoch": 44.61538461538461,
|
| 10445 |
+
"grad_norm": 0.0,
|
| 10446 |
+
"learning_rate": 2.1005e-05,
|
| 10447 |
+
"loss": 1.6964,
|
| 10448 |
+
"mean_token_accuracy": 0.6554509729146958,
|
| 10449 |
+
"num_tokens": 21152459.0,
|
| 10450 |
+
"step": 5800
|
| 10451 |
}
|
| 10452 |
],
|
| 10453 |
"logging_steps": 5,
|
|
|
|
| 10467 |
"attributes": {}
|
| 10468 |
}
|
| 10469 |
},
|
| 10470 |
+
"total_flos": 1.0719022971307622e+18,
|
| 10471 |
"train_batch_size": 4,
|
| 10472 |
"trial_name": null,
|
| 10473 |
"trial_params": null
|